© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 763
    Prev
    Next
    INDEX
    Explanations

    lift

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    óm
    -0.41
     olev
    -0.40
    ac
    -0.40
    wildcard
    -0.38
    ́ng
    -0.37
    MemoryWarning
    -0.36
     siguen
    -0.36
    mstyle
    -0.35
    Nationalité
    -0.35
    kom
    -0.34
    POSITIVE LOGITS
     up
    1.08
     ProtoMessage
    0.81
     autorytatywna
    0.80
     referenties
    0.77
    protoimpl
    0.75
     weights
    0.71
    principalColumn
    0.71
     estimés
    0.71
    AnimationsModule
    0.71
     Up
    0.68
    Activations Density 0.002%

    No Known Activations